Back to search

University of Alabama Birmingham

Functional Least Squares Minimization

Abstract

dc:description.abstract

In this thesis, we forecast the trend and price of a selected stock using four new algorithms and a previous mathematical model built from economic ‘tendencies’. We use a new variational regularization method to determine the coefficients of the delay differential equation in the previous mathematical model. We also apply our new approach to obtaining initial points for the regularization method as well as a technique for mitigating the exponential growth model error throughout the minimization process of the regularization method. Lastly, we use the newly discovered coefficients together with a new iterative improvement procedure and a knowledge of the stock volatility to greatly improve the price prediction. We compare our model’s predictions to actual stock prices, forecasts from a previous model, and predictions from a deep learning model.

Degree

thesis:*
Level thesis:degree_level
Dissertation

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Cox, Kyoung Joo
Contributors dc:contributor
  • Ian W Knowles
  • Shangbing Ai
  • Marius N Nkashama
  • Roger B Sidje
  • Chengcui Zhang

Subjects

dc:subject × 1

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
University of Alabama Birmingham
Base URL
digitalcommons.library.uab.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Cox, Kyoung Joo. Functional Least Squares Minimization. Dissertation thesis, https://digitalcommons.library.uab.edu/etd-collection/440